Training in progress, step 45, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 191968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e016df494cd1a20becf8b304b437acc58ebc4b3a2fe00342fff5babeb01b248
|
3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 253144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:040354bd2dad7f5b261b7da4a7ae50a8ba97d32dca488aa3d9def588806bd98a
|
3 |
size 253144
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8f44828df8830151d896be841876dc9cee379b27bb94793e2085a5033e38e02
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -170,6 +170,28 @@
|
|
170 |
"eval_samples_per_second": 471.976,
|
171 |
"eval_steps_per_second": 118.033,
|
172 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
173 |
}
|
174 |
],
|
175 |
"logging_steps": 3,
|
@@ -189,7 +211,7 @@
|
|
189 |
"attributes": {}
|
190 |
}
|
191 |
},
|
192 |
-
"total_flos":
|
193 |
"train_batch_size": 4,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008294739752540263,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
170 |
"eval_samples_per_second": 471.976,
|
171 |
"eval_steps_per_second": 118.033,
|
172 |
"step": 40
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.007741757102370913,
|
176 |
+
"grad_norm": 0.14071166515350342,
|
177 |
+
"learning_rate": 9.549150281252633e-06,
|
178 |
+
"loss": 10.3592,
|
179 |
+
"step": 42
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.008294739752540263,
|
183 |
+
"grad_norm": 0.18590952455997467,
|
184 |
+
"learning_rate": 3.8060233744356633e-06,
|
185 |
+
"loss": 10.3607,
|
186 |
+
"step": 45
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.008294739752540263,
|
190 |
+
"eval_loss": 10.360003471374512,
|
191 |
+
"eval_runtime": 19.526,
|
192 |
+
"eval_samples_per_second": 467.94,
|
193 |
+
"eval_steps_per_second": 117.023,
|
194 |
+
"step": 45
|
195 |
}
|
196 |
],
|
197 |
"logging_steps": 3,
|
|
|
211 |
"attributes": {}
|
212 |
}
|
213 |
},
|
214 |
+
"total_flos": 5019779727360.0,
|
215 |
"train_batch_size": 4,
|
216 |
"trial_name": null,
|
217 |
"trial_params": null
|